# VISION

BLACKBOX Vision provides users with the ability to instruct BLACKBOX AI to analyze image or video inputs, such as code screenshots or product sketches. 

This feature allows for a deeper exploration of visual elements, thereby paving the way for a more precise and detailed understanding of the information contained within these media.

To use it, simply click on the paperclip icon to the left of the text input to insert an image or video for analysis.

<figure><img src="/files/MYk3gLP15yFNxTYYElzx" alt=""><figcaption><p>Add Image or Vidéo to activate VISION</p></figcaption></figure>

Here's a demo of using Vision with an image.

{% embed url="<https://drive.google.com/file/d/1kgjTNbGjvpC9CY6yCEslFDeLnMNdb34S/view?usp=drive_link>" %}
BLACKBOX AI Vision Example
{% endembed %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.blackbox.chat/blackbox-ai-1/website/website-old/vision.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.